Google DeepMind 推出了 AI 联合临床医生研究计划，旨在协助医疗专业人员和患者。该系统利用实时视频和音频分析患者的步态或呼吸等身体症状。在测试中，该 AI 在 140 个评估领域中的 68 个领域（包括分诊）表现强劲，与医生相当或超越医生，并在 NOHARM 安全框架下处理的 98 个初级保健查询中，有 97 个查询未出现重大错误。 AI
影响 通过多模态 AI 分析，有潜力增强临床决策能力并改善患者护理。
排序理由 研究计划发布，包含来自主要 AI 实验室的测试结果。
AI 生成摘要 · Google Gemini · 来自 6 个来源。 我们如何撰写摘要 →
We’re advancing this research with academics and institutions globally, and will gradually expand our clinician-facing trusted tester program to additional sites - to understand more perspectives of health workers and patients worldwide. Find out more → https://t.co/c1dA6iS166 h…
To keep patient safety at the forefront, the system also runs on a dual agent architecture. A built-in "Planner" continuously monitors the conversation verifying that the "Talker" agent stays within safe clinical boundaries. https://t.co/X40w7h4hHo
In testing, AI co-clinician matched or outperformed physicians in 68 out of 140 assessed areas, including triage. Yet humans were easily better at spotting crucial red flags and guiding physical exams - showing how these tools could augment clinical judgment. See the benchmarks …
The system uses live video and audio to process physical symptoms in real-time. This means it could analyze a patient's walk, listen to their breathing, or look at how a rash is appearing. Alongside physicians from @Harvardmed and @StanfordMed, we created a simulation study with…
Our research goal for AI co-clinician is to support medical decision making with high-quality evidence. We tested the system while adapting the NOHARM safety framework, and found it made zero critical errors in 97 of 98 primary care queries - outperforming comparable systems in …
AI co-clinician is our new research initiative to help explore how multimodal agents could better support healthcare workers and patients. 🩺 Here’s a snapshot of our progress 🧵 https://t.co/7NbhQRzotE